Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 871 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.5234. Min Act: -0.1700

Data Index: 2616466 (Open Web Text)

Max Activating Token Index: 120

Text #1

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.4871. Min Act: -0.1700

Data Index: 5710884 (Open Web Text)

Max Activating Token Index: 491

Text #2

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.3847. Min Act: -0.1700

Data Index: 4998260 (Open Web Text)

Max Activating Token Index: 123

Text #3

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.4014. Min Act: -0.1700

Data Index: 8762011 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.4709. Min Act: -0.1700

Data Index: 3505103 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.4182. Min Act: -0.1700

Data Index: 1461608 (Open Web Text)

Max Activating Token Index: 488

Text #6

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.3249. Min Act: -0.1700

Data Index: 8155702 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.3205. Min Act: -0.1700

Data Index: 7434860 (Open Web Text)

Max Activating Token Index: 373

Text #8

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.2351. Min Act: -0.1700

Data Index: 4563568 (Open Web Text)

Max Activating Token Index: 797

Text #9

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.2949. Min Act: -0.1700

Data Index: 7467929 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.2654. Min Act: -0.1700

Data Index: 79465 (Open Web Text)

Max Activating Token Index: 228

Text #11

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.2717. Min Act: -0.1700

Data Index: 2628211 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.2774. Min Act: -0.1700

Data Index: 6984116 (Open Web Text)

Max Activating Token Index: 574

Text #13

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.2159. Min Act: -0.1700

Data Index: 895127 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.2171. Min Act: -0.1700

Data Index: 5592678 (Open Web Text)

Max Activating Token Index: 259

Text #15

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.2197. Min Act: -0.1700

Data Index: 2311733 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.1731. Min Act: -0.1700

Data Index: 2749807 (Open Web Text)

Max Activating Token Index: 365

Text #17

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.1786. Min Act: -0.1700

Data Index: 5070299 (Open Web Text)

Max Activating Token Index: 955

Text #18

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.2189. Min Act: -0.1700

Data Index: 5100023 (Open Web Text)

Max Activating Token Index: 622

Text #19

Max Range: 7.5234. Min Range: -7.5234

Max Act: 7.1662. Min Act: -0.1700

Data Index: 3164998 (Open Web Text)

Max Activating Token Index: 499